Deze Zeng

• Professor
• Professor at China University of Geosciences

Transformers have dominated the field of natural language processing, attributed to their capability to handle sequential input data. There is a surge of work on computational and networking optimizations, aimed at improving the training efficiency of Transformers. However, transformer inference, a cornerstone of myriad AI services, remains relativ...

Thanks to the capability of fine-grained resource allocation and fast task scheduling, serverless computing has been adopted into edge cloud to accommodate various applications, e.g., DNN inference for Artificial Intelligence of Things (AIoT). In serverless edge cloud, the servers are started up on-demand. However, as a container-based architecture...

User-facing applications often experience excessive loads and are shifting towards the microservice architecture. To fully utilize heterogeneous resources, current datacenters have adopted the disaggregated storage and compute architecture, where the storage and compute clusters are suitable to deploy the stateful and stateless microservices, respe...

The prosperity of machine learning applications has promoted the rapid development of GPU architecture. It continues to integrate more CUDA Cores, larger L2 cache and memory bandwidth within SM. Moreover, the GPU integrates Tensor Core dedicated to matrix multiplication. Although studies have shown that task co-location could effectively improve sy...

Interest flooding attacks (IFAs) has been regarded as some of the most harmful security risks in named data networks (NDNs), and they have always been highly important in the next-generation network security field. In recent years, a variant and upgraded version of the original IFA named a collusive IFA (CIFA) has been witnessed. Since a CIFA is la...

While deep neural network (DNN) models are mainly trained using GPUs, many companies and research institutions build shared GPU clusters. These clusters host DNN training jobs, DNN inference jobs, and CPU jobs (jobs in traditional areas). DNN training jobs require GPU for main computation and CPU for auxiliary computation. Some DNN inference jobs c...

Federated Distillation (FD) extends classic Federated Learning (FL) to a more general training framework that enables model-heterogeneous collaborative learning by Knowledge Distillation (KD) across multiple clients and the server. However, existing KD-based algorithms usually require a set of shared input samples for each client to produce soft-pr...

By leveraging standard IT virtualization technology and Commercial-Off-The-Shelf (COTS) servers, Network Function Virtualization (NFV) decouples network functions from proprietary hardware devices for flexible service provisioning. But the potential of NFV is significantly limited by its performance inefficiency. With the unparalleled advantages of...

Time series data mining techniques have attracted extensive attention from researchers worldwide. Of these techniques, time series classification is an important part of time series mining. Among the many time series classification algorithms, methods based on the bag-of-patterns algorithm have attracted much attention from researchers because of t...

Task offloading to edge servers has become a promising solution to tackle the computation resource poverty of the end devices. However, the zero-trust edge computing platform is highly challenged by the growing concern on security and privacy. Thus, Trust Execution Environment (TEE), like TrustZone, is advocated to empower edge clouds to enable sec...

Offloading tasks to edge servers has been regarded as a potential way to solve the computation resource poverty problem of the end devices like autonomous vehicles. However, due to the sharing and openness features of edge computing, it raises severe security problems. In order to combat such issues, Trust Execution Environment (TEE), such as Trust...

Underwater acoustic sensor networks (UASNs) are among the most critical tools for underwater environment sensing and information acquisition. Since the complexity of the underwater environment renders battery replenishment and replacement more difficult and UASNs are mainly powered by batteries built into the underwater acoustic sensor nodes, the o...

Underwater acoustic sensor networks (UASNs) currently provide an important technical means of underwater communication, but there are difficulties in power updating or power replenishment because the sensor nodes work in an underwater environment. Therefore, energy consumption optimization has become the focus of research on UASNs. Node clustering...

Most of the existing FL systems focus on a data-parallel architecture where training data are partitioned by samples among several parties. In some real-life applications, however, partitioning by features is also of practical relevance and the number of features is usually unbalanced among parties. The corresponding learning framework is referred...

Edge intelligence has emerged as a prevalent enabling technology to support various intelligent applications. Along with the prosperity, it also raises great concern on the security and privacy since the edge servers are usually shared and untrusted. The security-sensitive code (i.e., the pre-trained model) and data may be easily stolen by maliciou...

Offloading computation tasks through cloud–edge collaboration has been a promising way to improve the Quality of Service (QoS) of applications. Usually, cloud server (CS) and edge server (ES) are selfish and rational and, therefore, it is imperative to develop incentive mechanisms, which can encourage idle ESs or the CS to participate in the task o...

To bridge the performance gap between network and storage, performance tuning of file systems according to different workloads has become an important work on the Internet of Things (IoT). However, existing methods on file system tuning mainly focused on tailoring the file system kernel codes, or cannot scope to high dimensional parameters and dyna...

Non-volatile memory, also called persistent memory (PM), has the features of byte addressing, non-volatility and the similar performance with traditional DRAM, but still shows obvious latency in several common scenarios which adopt the synchronous (sync) I/O, such as the application transferring large PM data or accessing the remote PM data in a NU...

Edge computing has become an alternative low-latency provision of cloud computing thanks to its close-proximity to the users, and the geo-distribution nature of edge servers enables the utilization green energy from the environment on-site. To pursue the goal of low-carbon edge computing, it is desirable to minimize the operational expenditure by s...

Internet-of-Things (IoT) has been widely applied in various domains during the past decades. However, battery-powered IoT devices are notorious for the limited lifetime due to the limitation on the battery capability. Lots of methods have been proposed to promote the energy efficiency so as to prolong the network lifetime for sustainable, and even...

User-facing services are now evolving towards the microservice architecture where a service is built by connecting multiple microservice stages. Since the entire service is heavy, the microservice architecture shows the opportunity to only offload some microservice stages to the edge devices that are close to the end users. However, emerging techni...

Recent advances in virtualization technologies (e.g., uniker-nels, containers, and virtual machines), the move to data driven approaches and softwarized networking technologies (e.g., SDN, NFV, and data plane programming) have invigorated a new focus on combining computation and communication in distributed systems. At the same time, the proliferat...

IoT anomaly detection is significant due to its fundamental roles of securing modern critical infrastructures. Researchers have proposed various detection methods fostered by machine learning (ML) techniques. Federated learning (FL),as a promising distributed ML paradigm,has been employed recently to improve detection performance due to its advanta...

Federated learning (FL) has been widely recognized as a promising approach by enabling individual end-devices to cooperatively train a global model without exposing their own data. One of the key challenges in FL is the non-independent and identically distributed (Non-IID) data across the clients, which decreases the efficiency of stochastic gradie...

Vehicular named data networking (V-NDN) is a network architecture that combines named data networking (NDN) and vehicular ad hoc networks (VANETs). Due to the high-speed mobility of the on-board unit (OBU) in V-NDNs, topological changes may cause the problem of reverse path breaking for data packets, thus impacting the communication quality of serv...

Cloud radio access network (C-RAN) has been widely regarded as a promising techniques for 5G cellular mobile communication. By decoupling radio and baseband processing from all-in-one macro base station into remote radio head (RRH) and baseband unit (BBU) pool, C-RAN can significantly improve the flexibility and scalability of cellular mobile syste...

Named data networking(NDN) is one representation and implementation of information-centric networking(ICN) and is considered to be among the most promising designs for the next generation of network architecture. The introduction of NDN into vehicular ad-hoc networks (VANETs) and utilization of its content-centric characteristic to improve data tra...

Efficient urban traffic monitoring is a key enabler for intelligent planning and management of modern cities. Network tomography can monitor the urban traffic with a comparably small number of traffic detectors like cameras, and has become an appealing technique for urban traffic management. However, previous work on network tomography based traffi...

As a rising star of social apps, short video apps, e.g., TikTok, have attracted a large number of mobile users by providing fresh and short video contents that highly match their watching preferences. Meanwhile, the booming growth of short video apps imposes new technical challenges on the existing computation and communication infrastructure. Trad...

Interest flooding attacks (IFAs) are widely regarded as being among the most harmful security risks in named data networking (NDN). Through an IFA, the attacker injects numerous Interest packets into a network to drain network resources such as bandwidth, caching capacity, and computational capacity, which can seriously affect the normal data conte...

Large-scale datacenters often host latency-sensitive services that have stringent Quality-of-Service requirement and experience diurnal load pattern. Co-locating best-effort applications that have no QoS requirement with the latency-sensitive services has been widely used to improve the resource utilization of datacenters with careful shared resour...

The Underwater acoustic sensor network (UASN) is a specific deployment of Internet-of-Things (IoT) technology in underwater environment, since energy constraints limit the lifetime of underwater acoustic sensor networks (UASNs), effectively balancing the energy consumption of acoustic sensor nodes in UASNs is important to maximize the amount of inf...

Network Function Virtualization (NFV), as an emerging solution to virtualizing network services traditionally running on proprietary, dedicated devices, can effectively reduce the cost of big data processing service providers and improve service quality by running a service chain of ordered Virtual Network Functions (VNFs) on commodity hardware. On...

As VANETs have been widely applied in various fields including entertainment and safety- related applications like autonomous driving, malicious intrusions into VANETs may lead to disastrous results. Hence, intrusion detection accuracy as well as efficiency is sensitive to the normal operation of VANETs. Regarding this, in this article we propose a...

Hosting virtualized network functions (VNF) has been regarded as an effective way to realize network function virtualization (NFV). Considering the cost diversity in cloud computing, from the perspective of service providers, it is significant to orchestrate the VNFs and schedule the traffic flows for network utility maximization (NUM) as it implie...

Internet of Things (IoT) generates large amounts of data at the network edge. Machine learning models are often built on these data, to enable the detection, classification, and prediction of future events. Due to network bandwidth, storage, and especially privacy concerns, it is often impossible to send all the IoT data to the data center for cent...

In this book, we introduce the concept and architecture of software defined systems (SDS). The core enabling technologies, including software defined front-end devices (sensors, IoT devices), software defined access networks (e.g., cognitive radio, CRAN), software defined core networks (e.g., SDN, NFV), software defined storage and computing (e.g.,...

After a decade of extensive research on application-specific WSNs, the recent development of information and communication technologies makes it practical to realize SDSNs, which are able to adapt to various application requirements and to fully explore the resources of WSNs. A sensor node in SDSN is able to conduct multiple tasks with different se...

Software defined network (SDN) is a newly emerging network architecture with the core concept of separating the control plane and data plane. Centralized controller is introduced to manage and configure network equipments to realize flexible control of network traffic and provide a good platform for application-oriented network innovation. It thus...

Capillary networks are regarded as essential compliments to cellular networks for future smart city applications. Gateways play a critical role to interconnect capillary networks with the Internet. However, traditional purpose-built hardware based gateways are not flexible enough to accommodate the emerging diverse radio access technologies and sat...

Cloud radio access network (C-RAN) has been widely regarded as a promising techniques for 5G cellular mobile communication. By decoupling radio and baseband processing from all-in-one macro base station into remote radio head (RRH) and baseband unit (BBU) pool, C-RAN can significantly improve the flexibility and scalability of cellular mobile syste...

This book introduces the software defined system concept, architecture, and its enabling technologies such as software defined sensor networks (SDSN), software defined radio, cloud/fog radio access networks (C/F-RAN), software defined networking (SDN), network function virtualization (NFV), software defined storage, virtualization and docker. The a...

The fast development of mobile computing has raised ever-increasing diverse communication needs in wireless networks. To catch up with such needs, cloud-radio access networks (CRAN) is proposed to enable efficient radio resource sharing and management. By CRAN, it is possible to realize software defined access networks. At the same time, the massiv...

Network function virtualization (NFV) emerges as a promising technology to increase the network flexibility, customizability, and efficiency by softwarizing traditional dedicated hardware based functions to virtualized network functions. The prosperous potential of edge cloud makes it an ideal platform to host the network functions. From the perspe...

Accurate knowledge of network topology is vital for network monitoring and management. Network tomography can probe the underlying topologies of the intervening networks solely by sending and receiving packets between end hosts: the performance correlations of the end-to-end paths between each pair of end hosts can be mapped to the lengths of their...

Mobile edge computing (MobEC) builds an Information Technology (IT) service environment to enable cloud-computing capabilities at the edge of mobile networks. To tackle the restrictions in the battery power and computation capability of mobile devices, task offloading for using MobEC is developed and used to reduce the service latency and to ensure...

Edge computing has been regarded as an ideal platform to provision computation and storage resources at the network edge thanks to its vast distribution and user proximity. Owing to such features, it is also promising to provision energy resources at the network edge via wireless energy transferring. With the consideration of the mobility of wirele...

Big data analytics in datacenters often involves scheduling of data-parallel jobs. Traditional scheduling techniques based on improving network resource utilization are subject to limited bandwidth. To alleviate the shortage of bandwidth, some cluster frameworks employ techniques of traffic compression to reduce transmission consumption. However, t...

Network congestion will result in significant performance degradation or even failures of many bandwidth-hungry Internet of Things (IoT) applications. Accurate and efficient congested link identification has become a foundational issue to IoT applications like self-driving cars, digital health, smart city, and so on. However, directly monitoring th...

Dataflow computing has become a promising computing paradigm as an alternative to traditional control‐centric computing paradigm to facilitate big data processing. Big data process often happens in cloud computing environment as the datacenter provisions a large amount of resource. Dataflow computing, as a data‐centric computing paradigm, requires...

The spread of the sensors and industrial systems has fostered widespread real-time data processing applications. Massive vector field data (MVFD) are generated by vast distributed sensors and are characterized by high distribution, high velocity, and high volume. As a result, computing such kind of data on centralized cloud faces unprecedented chal...

Wireless networks have experienced fast development in the past decades. Various advancing wireless technologies have been proposed. To catch up with the ever-increasing diverse communication needs, cloud-radio access networks (C-RAN), which decouples the baseband processing unit (BBU) from the remote radio head (RRH), has been proposed. On the oth...

With the advent of edge computing, it is highly recommended to extend some cloud services to the network edge such that the services can be provisioned in the proximity of end users, with better performance efficiency and cost efficiency. Compared to cloud computing, edge computing has high dynamics, and therefore the resources shall be correspondi...